π¬ AMP Candidates
2,065 computationally predicted antimicrobial peptide candidates
𧬠About these candidates
Each candidate was identified by mining extreme-environment metagenomes with ESM-2, a protein language model trained on 250M sequences. Candidates pass multi-stage filtering: biophysical scoring, novelty screening against 863K known AMPs (APD3 + DRAMP + AMPSphere), hemolysis risk prediction, and structural validation via AlphaFold2.
β οΈ All candidates are computationally predicted β no experimental validation has been performed.
π Hot Springs
0.9214
π Hot Springs
0.9214
π Hot Springs
0.9214
π Hot Springs
0.9213
π Hot Springs
0.9210
π Hot Springs
0.9210
π Hot Springs
0.9209
π Hot Springs
0.9207
π Hot Springs
0.9207
π Hot Springs
0.9207
π Hot Springs
0.9205
π Hot Springs
0.9205
π Hot Springs
0.9205
π Hot Springs
0.9204
π Hot Springs
0.9204
π Hot Springs
0.9203
π Hot Springs
0.9202
π Hot Springs
0.9202
π Hot Springs
0.9202
π Hot Springs
0.9201
π Hot Springs
0.9201
π Hot Springs
0.9201
π Hot Springs
0.9200
π Hot Springs
0.9199
π Understanding the metrics